Moyano, Jose M.Ventura, Sebastian
19页查看更多>>摘要：Multi-label classification has been used to solve a wide range of problems where each example in the dataset may be related either to one class (as in traditional classification problems) or to several class labels at the same time. Many ensemble-based approaches have been proposed in the literature, aiming to improve the performance of traditional multi-label classification algorithms. However, most of them do not consider the data characteristics to build the ensemble, and those that consider them need to tune many parameters to maximize their performance. In this paper, we propose an Auto-adaptive algorithm based on Grammar-Guided Genetic Programming to generate Ensembles of Multi-Label Classifiers based on projections of k labels (AG3P-kEMLC). It creates a tree-shaped ensemble, where each leaf is a multi-label classifier focused on a subset of k labels. Unlike other methods in the literature, our proposal can deal with different values of k in the same ensemble, instead of fixing one specific value. It also includes an auto-adaptive process to reduce the number of hyper-parameters to tune, prevent overfitting and reduce the runtime required to execute it. Three versions of the algorithm are proposed. The first, fixed, uses the same value of k for all multi-label classifiers in the ensemble. The remaining two deal with different k values in the ensemble: uniform gives the same probability to choose each available value of k, and gaussian favors the selection of smaller values of k. The experimental study carried out considering twenty reference datasets and five evaluation metrics, compared with eleven ensemble methods demonstrates that our proposal performs significantly better than the state-of-the-art methods.
原文链接:
NSTL
Elsevier
Arun, P., VSadeh, R.Avneri, A.Tubul, Y....
20页查看更多>>摘要：Multiple and heterogenous Earth observation (EO) platforms are broadly used for a wide array of applications, and the integration of these diverse modalities facilitates better extraction of information than using them individually. The detection capability of the multispectral unmanned aerial vehicle (UAV) and satellite imagery can be significantly improved by fusing with ground hyperspectral data. However, variability in spatial and spectral resolution can affect the efficiency of such dataset's fusion. In this study, to address the modality bias, the input data was projected to a shared latent space using cross-modal generative approaches or guided unsupervised transformation. The proposed adversarial networks and variational encoder-based strategies used bidirectional transformations to model the cross-domain correlation without using cross-domain correspondence. It may be noted that an interpolation-based convolution was adopted instead of the normal convolution for learning the features of the point spectral data (ground spectra). The proposed generative adversarial networkbased approach employed dynamic time wrapping based layers along with a cyclic consistency constraint to use the minimal number of unlabeled samples, having cross-domain correlation, to compute a cross-modal generative latent space. The proposed variational encoder-based transformation also addressed the cross-modal resolution differences and limited availability of cross-domain samples by using a mixture of expert-based strategy, cross-domain constraints, and adversarial learning. In addition, the latent space was modelled to be composed of modality independent and modality dependent spaces, thereby further reducing the requirement of training samples and addressing the cross-modality biases. An unsupervised covariance guided transformation was also proposed to transform the labelled samples without using cross-domain correlation prior. The proposed latent space transformation approaches resolved the requirement of cross-domain samples which has been a critical issue with the fusion of multi-modal Earth observation data. This study also proposed a latent graph generation and graph convolutional approach to predict the labels resolving the domain discrepancy and cross-modality biases. Based on the experiments over different standard benchmark airborne datasets and real-world UAV datasets, the developed approaches outperformed the prominent hyperspectral panchromatic sharpening, image fusion, and domain adaptation approaches. By using specific constraints and regularizations, the network developed was less sensitive to network parameters, unlike in similar implementations. The proposed approach illustrated improved generalizability in comparison with the prominent existing approaches. In addition to the fusion-based classification of the multispectral and hyperspectral datasets, the proposed approach was extended to the classification of hyperspectral airborne datasets where the latent graph generation and convolution were employed to resolve the domain bias with a small number of training samples. Overall, the developed transformations and architectures will be useful for the semantic interpretation and analysis of multimodal data and are applicable to signal processing, manifold learning, video analysis, data mining, and time series analysis, to name a few.
原文链接:- NSTL
- Elsevier
Wang, WeizhongDing, LingLiu, XinwangLiu, Shuli...
17页查看更多>>摘要：The risk assessment is one of the most significant procedures for identifying, preventing, and controlling Occupational Health and Safety (OHS) risks. One of many kinds of techniques for OHS risk assessment is based on the Fine-Kinney model. Most of the Fine-Kinney-based risk assessment approaches can consider the relative importance degree of risk parameters. Nevertheless, the current Fine-Kinney-based risk assessment approaches do not have abilities to capture the reference dependence effects and detailed relationships among hazards. In addition, these approaches overlook the influence of the deviation of risk evaluation information. To overcome these limitations, in this paper, an improved Fine-Kinney model is proposed for OHS risk assessment by integrating the weighted power average (WPA) operator, ORESTE (Organisation, rangement et Synthe`se de donne acute accent es relarionnelles (in French)) method, and cumulative prospect theory. First, the interval 2-Tuple linguistic variables are adopted to transform linguistic risk information into quantitative risk rating information. Then, an extended WPA operator is proposed to fuse the risk evaluation information from decision-makers, in which an optimization model is constructed to determine the weights of decision-makers. Next, an extended ORESTE method based on cumulative prospect theory and interval 2-Tuple linguistic variables is incorporated into the Fine-Kinney model to prioritize OHS risk. After that, the OHS risk assessment of the automobile components manufacturing process is presented to test the applicability and rationality of the improved Fine-Kinney model. After that, a sensitivity analysis is conducted to further illustrate the proposed model. Finally, the comparative analyses between the proposed risk assessment approach and other Fine-Kinney models are led to illustrating its effectiveness and advantages.
原文链接:- NSTL
- Elsevier
Celik, Y.Stuart, S.Woo, W. L.Sejdic, E....
14页查看更多>>摘要：Gait abnormalities are typically derived from neurological conditions or orthopaedic problems and can cause severe consequences such as limited mobility and falls. Gait analysis plays a crucial role in monitoring gait abnormalities and discovering underlying deficits can help develop rehabilitation programs. Contemporary gait analysis requires a multi-modal gait analysis approach where spatio-temporal, kinematic and muscle activation gait characteristics are investigated. Additionally, protocols for gait analysis are going beyond labs/clinics to provide more habitual insights, uncovering underlying reasons for limited mobility and falls during daily activities. Wearables are the most prominent technology that are reliable and allow multi-modal gait analysis beyond the labs/clinics for extended periods. There are established wearable-based algorithms for extracting informative gait characteristics and interpretation. This paper proposes a multi-layer fusion framework with sensor, data and gait characteristics. The wearable sensors consist of four units (inertial and electromyography, EMG) attached to both legs (shanks and thighs) and surface electrodes placed on four muscle groups. Inertial and EMG data are interpreted by numerous validated algorithms to extract gait characteristics in different environments. This paper also includes a pilot study to test the proposed fusion approach in a small cohort of stroke survivors. Experimental results in various terrains show healthy participants experienced the highest pace and variability along with slightly increased knee flexion angles (approximate to 1 degrees) and decreased overall muscle activation level during outdoor walking compared to indoor, incline walking activities. Stroke survivors experienced slightly increased pace, asymmetry, and knee flexion angles (approximate to 4 degrees) during outdoor walking compared to indoor. A multimodal approach through a sensor, data and gait characteristic fusion presents a more holistic gait assessment process to identify changes in different testing environments. The utilisation of the fusion approach presented here warrants further investigation in those with neurological conditions, which could significantly contribute to the current understanding of impaired gait.
原文链接:- NSTL
- Elsevier
Chen, XiaohongZhang, WeiweiXu, XuanhuaCao, Wenzhi...
15页查看更多>>摘要：With the rapid development of social media, reliable information released by the public on social media can provide important decision-making support. Therefore, the consideration of the public as another decisionmaking body participating in large-scale group decision-making (LSGDM) problems has become an extensively researched topic. However, the participation of the public as a decision-making body with decision-making experts faces several issues, such as the acquisition of public opinion, the reliability of public opinion, the integration of public and expert opinions, etc. Given this, this paper proposes a public and large-scale expert information fusion method that considers public dynamic reliability via sentiment analysis and intuitionistic fuzzy number (IFN) expressions. First, sentiment analysis technology is used to process public social media data and obtain IFNs as the opinions of the public decision-making body. Second, the concept of public dynamic reliability is defined to measure the degree of integration of public opinion. Third, a novel information entropy measure of IFNs is proposed, and a new method is introduced to determine the criteria weights under the two different decision-making bodies. Finally, an optimization model that considers the consensus levels of expert subgroups is proposed to determine the weights of different decision-making bodies. The public and expert opinions are then aggregated to obtain collective decision-making information. A case study is proposed to illustrate the application of the proposed method, and the comparative analysis reveals the features and advantages of this model.
原文链接:- NSTL
- Elsevier
Wan, LiangtianLiu, RongSun, LuWang, Xianpeng...
12页查看更多>>摘要：Traditional clustering algorithms can be applied for the pre-sorting step of radar signal sorting. It can effectively dilute the pulse stream and prevent the dense pulse stream from interfering pulse repetition interval (PRI) extraction. However, the pre-sorting deviation will cause interference and missing pulses during the main sorting process. To solve this problem, we deploy the unmanned aerial vehicle (UAV) swarm to monitor reconnaissance areas and put forward a novel deep transfer learning based signal sorting method. The UAV swarm can collect the pulses from different time and spatial domains, and interference and missing pulses in main sorting processing can be relieved dramatically. In our model, we pre-train our model with the data collected from multiple source areas, which corresponds to different areas detected by different parts of UAV swarms. Then we fine-tune our model with the data of the target area. The experimental results prove that the signal sorting accuracy of methods based on deep transfer learning, i.e., YOLO-MobileNet, F-RCNN and cascade RCNN, are higher than that of the baseline methods. In addition, the signal sorting accuracy of traditional methods based on deep learning can be greatly improved with the help of transfer learning.
原文链接:- NSTL
- Elsevier
Gutierrez, RaulRamperez, VictorPaggi, HoracioLara, Juan A....
36页查看更多>>摘要：The information fusion field has recently been attracting a lot of interest within the scientific community, as it provides, through the combination of different sources of heterogeneous information, a fuller and/or more precise understanding of the real world than can be gained considering the above sources separately. One of the fundamental aims of computer systems, and especially decision support systems, is to assure that the quality of the information they process is high. There are many different approaches for this purpose, including information fusion. Information fusion is currently one of the most promising methods. It is particularly useful under circumstances where quality might be compromised, for example, either intrinsically due to imperfect information (vagueness, uncertainty, ...) or because of limited resources (energy, time, ... ). In response to this goal, a wide range of research has been undertaken over recent years. To date, the literature reviews in this field have focused on problem-specific issues and have been circumscribed to certain system types. Therefore, there is no holistic and systematic knowledge of the state of the art to help establish the steps to be taken in the future. In particular, aspects like what impact different information fusion methods have on information quality, how information quality is characterised, measured and evaluated in different application domains depending on the problem data type or whether fusion is designed as a flexible process capable of adapting to changing system circumstances and their intrinsically limited resources have not been addressed. This paper aims precisely to review the literature on research into the use of information fusion techniques specifically to improve information quality, analysing the above issues in order to identify a series of challenges and research directions, which are presented in this paper.
原文链接:- NSTL
- Elsevier
Zhang, DanYe, MaoXiong, LinZhou, Lihua...
11页查看更多>>摘要：Domain adaptation for object detection has been extensively studied in recent years. Most existing approaches focus on single-source unsupervised domain adaptive object detection. However, a more practical scenario is that the labeled source data is collected from multiple domains with different feature distributions. The conventional approaches do not work very well since multiple domain gaps exist. We propose a Multi-source domain Knowledge Transfer (MKT) method to handle this situation. First, the low-level features from multiple domains are aligned by learning a shallow feature extraction network. Then, the high-level features from each pair of source and target domains are aligned by the followed multi-branch network. After that, we perform two parts of information fusion: (1) We train a detection network shared by all branches based on the transferability of each source sample feature. The transferability of a source sample feature means the indistinguishable degree to the target domain sample features. (2) For using our model, the target sample features output by the multi-branch network are fused based on the average transferability of each domain. Moreover, we leverage both image-level and instance-level attention to promote positive cross-domain transfer and suppress negative transfer. Our main contributions are the two-stage feature alignments and information fusion. Extensive experimental results on various transfer scenarios show that our method achieves the state-of-the-art performance.
原文链接:- NSTL
- Elsevier
Lin, HuiGarg, SahilHu, JiaWang, Xiaoding...
9页查看更多>>摘要：In the Internet of Things (IoT), a huge amount of valuable data is generated by various IoT applications. As the IoT technologies become more complex, the attack methods are more diversified and can cause serious damages. Thus, establishing a secure IoT network based on user trust evaluation to defend against security threats and ensure the reliability of data source of collected data have become urgent issues, in this paper, a Data Fusion and transfer learning empowered granular Trust Evaluation mechanism (DFTE) is proposed to address the above challenges. Specifically, to meet the granularity demands of trust evaluation, time-space empowered fine/coarse grained trust evaluation models are built utilizing deep transfer learning algorithms based on data fusion. Moreover, to prevent privacy leakage and task sabotage, a dynamic reward and punishment mechanism is developed to encourage honest users by dynamically adjusting the scale of reward or punishment and accurately evaluating users' trusts. The extensive experiments show that: (i) the proposed DFTE achieves high accuracy of trust evaluation under different granular demands through efficient data fusion; (ii) DFTE performs excellently in participation rate and data reliability.
原文链接:- NSTL
- Elsevier
